CN113323818A - Yaw error measuring method and device for multiple types of fans - Google Patents

Yaw error measuring method and device for multiple types of fans Download PDF

Info

Publication number
CN113323818A
CN113323818A CN202110647957.5A CN202110647957A CN113323818A CN 113323818 A CN113323818 A CN 113323818A CN 202110647957 A CN202110647957 A CN 202110647957A CN 113323818 A CN113323818 A CN 113323818A
Authority
CN
China
Prior art keywords
data
equation
formula
wind speed
density
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110647957.5A
Other languages
Chinese (zh)
Other versions
CN113323818B (en
Inventor
庄勇
吴士华
林涛
王建君
李波函
王瑞祥
石琳
张哲�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Guodian Sida Technology Co ltd
Original Assignee
Beijing Guodian Sida Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Guodian Sida Technology Co ltd filed Critical Beijing Guodian Sida Technology Co ltd
Priority to CN202110647957.5A priority Critical patent/CN113323818B/en
Publication of CN113323818A publication Critical patent/CN113323818A/en
Application granted granted Critical
Publication of CN113323818B publication Critical patent/CN113323818B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Wind Motors (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a yaw error measuring method and a yaw error measuring device for a plurality of types of fans, wherein the method comprises the following steps: acquiring multi-type fan data, and preprocessing the multi-type fan data; and carrying out interval processing on the preprocessed data of the various types of fans, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of the various types of fans, and acquiring the yaw error of the various types of fans according to the optimal wind speed-power curve. The invention can simultaneously remove the discrete abnormal data and the accumulation abnormal data in the data set.

Description

Yaw error measuring method and device for multiple types of fans
Technical Field
The invention relates to the technical field of computers, in particular to a yaw error measuring method and device for a plurality of types of fans.
Background
In the prior art, wind energy is used as the second largest renewable energy source after water energy, the installed capacity space on the wind energy market is huge, investment on wind power is added in various countries, and due to the fact that the cost is low, the application form is flexible, the maintenance is simple, the technology is mature, and the wind energy is widely researched and applied in the whole world. According to the statistics of the 2019 world wind power union, although eight companies in China have entered fifteen strong before world fan manufacturers, the first two companies are occupied by the Wistar and the Simens and the West. At present, the direction for solving the problem is to analyze the operation data of the multiple types of fans by utilizing a big data technology to obtain the fan manufacturer with excellent yaw performance. Other types of fans are guided by learning the yaw control strategy of the fan, the static deviation of yaw systems of various fans is corrected, and the yaw performance of the unit is optimized.
The method is researched aiming at the static deviation of a yaw control system, and during the normal operation of a wind turbine generator set, the wind speed and the wind direction can be measured inaccurately due to a series of reasons such as eddy generated by rotation of a wind wheel or inaccurate installation of a wind direction indicator, so that the accuracy of data input by a yaw controller is influenced, and the yaw static error is generated. The prior art provides a wind vane measurement error calibration method of a wind turbine generator based on historical operating data, which eliminates abnormal data by adopting an improved DBSCAN clustering algorithm, corrects a wind direction indicator by using methods such as bi-harmonic spline interpolation and the like, and improves the generated energy of the wind turbine generator. However, the problem that the wind vane measures wind inaccurately still exists in the prior art.
Disclosure of Invention
The invention aims to provide a yaw error measuring method and device for a plurality of types of fans, and aims to solve the problems in the prior art.
The invention provides a yaw error measuring method of a multi-type fan, which comprises the following steps:
acquiring multi-type fan data, and preprocessing the multi-type fan data;
and carrying out interval processing on the preprocessed data of the various types of fans, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of the various types of fans, and acquiring the yaw error of the various types of fans according to the optimal wind speed-power curve.
The invention provides a yaw error measuring device of a multi-type fan, which comprises:
the acquisition module is used for acquiring the data of the multiple types of fans and preprocessing the data of the multiple types of fans;
and the processing module is used for carrying out interval processing on the preprocessed multi-type fan data, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of each type of fan, and acquiring the yaw error of each type of fan according to the optimal wind speed-power curve.
The embodiment of the present invention further provides a yaw error measuring apparatus for a multi-type fan, including: the yaw error measurement system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the steps of the yaw error measurement method of the multi-type wind turbine when being executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein an implementation program for information transmission is stored on the computer readable storage medium, and when the implementation program is executed by a processor, the steps of the yaw error measurement method for the multi-type fan are implemented.
By adopting the embodiment of the invention, the discrete abnormal data and the accumulation abnormal data in the data set can be removed simultaneously. In addition, the technical scheme of the embodiment of the invention is suitable for measuring the yaw error of different types of units, and can realize the comparison of the yaw performance of different types of fans.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a yaw error measurement method of a multi-type wind turbine according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart of a yaw error measurement method of a multi-type wind turbine according to an embodiment of the present invention;
FIG. 3a is a schematic diagram of direct density accessibility of DBSCAN algorithm principle of the present invention;
FIG. 3b is a schematic diagram of the density achievable by the DBSCAN algorithm principle of the embodiment of the present invention;
FIG. 3c is a schematic diagram of the density connection of the DBSCAN algorithm principle of the embodiment of the present invention;
FIG. 4 is a schematic diagram of an outlier recognition result based on an isolated forest and DBSCAN according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a cubic spline-fitted wind power curve of an embodiment of the present invention;
FIG. 6 is a schematic diagram of a class A fan compartmentalized power curve according to an embodiment of the invention;
FIG. 7 is a schematic illustration of a comparison of yaw performance of four types of wind turbines according to an embodiment of the present invention;
FIG. 8 is a schematic view of a yaw error measuring apparatus of a multi-type wind turbine according to a first embodiment of the present invention;
FIG. 9 is a schematic view of a yaw error measuring apparatus of a multi-type wind turbine according to a second embodiment of the present invention.
Detailed Description
Aiming at the problem that the wind measurement of a wind vane is inaccurate, the embodiment of the invention provides a yaw error measurement method of a multi-type fan. Firstly, cleaning abnormal data by adopting an isolated forest and DBSCAN clustering algorithm, carrying out normalization processing, carrying out interval processing on the obtained data, fitting the wind speed-power scattered points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve, and obtaining a yaw error. And obtaining the type of the fan with the optimal yaw performance by comparing the optimal wind speed-power curves of the four types of fans.
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise. Furthermore, the terms "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Method embodiment
According to an embodiment of the present invention, a yaw error measurement method for a multi-type fan is provided, fig. 1 is a flowchart of the yaw error measurement method for the multi-type fan according to the embodiment of the present invention, and as shown in fig. 1, the yaw error measurement method for the multi-type fan according to the embodiment of the present invention specifically includes:
step 101, acquiring multi-type fan data, and preprocessing the multi-type fan data;
and 102, performing interval processing on the preprocessed multi-type fan data, performing polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of each type of fan, and acquiring the yaw error of each type of fan according to the optimal wind speed-power curve.
In the embodiment of the invention, after the yaw errors of various types of fans are obtained according to the optimal wind speed-power curve, the optimal wind speed-power curve of various types of fans can be compared to obtain the type of the fan with the optimal yaw performance.
The technical solutions of the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Fig. 2 is a detailed flowchart of a yaw error measurement method of a multi-type wind turbine according to an embodiment of the present invention, and as shown in fig. 2, the method specifically includes the following steps:
s1: and acquiring data of the multiple types of fans.
In the embodiment, the data of four types of fans with good state in a certain wind power plant in North China for half a year are selected, the time is from the second level to the minute level, the smaller the time scale is, and the selected time range can be properly shortened. The data mainly comprises: time, wind angle, wind speed, power, wind direction, etc. The four types of fan data volumes are shown in table 1. And the state codes of the four types of fans are obtained, and a foundation is laid for subsequent elimination of abnormal data points.
TABLE 1 four Fan type data
Figure BDA0003109964230000061
S2: and (4) preprocessing data.
For the data acquired in S1, abnormal data needs to be removed, and in order to compare the performances of different fans, normalization processing needs to be performed on the data set.
S2.1: and the isolated forest isolates the abnormal points by aiming at the characteristics of small number of the abnormal points and large difference between the abnormal values and the normal values. The main idea is to divide the data set equally until all data points are isolated, and to judge whether the data points are abnormal points according to the score of each data point. The main process of an isolated forest is as follows:
(1) an isolated forest is composed of t isolated trees, represented as:
IF∈{t1,...,tT} (1)
wherein T is the total number of the isolated trees.
(2) For each tree t, the number of iterations ht (x) required to isolate a sample x can be calculated, and the average number of steps required to isolate a sample x in a forest is expressed as:
Figure BDA0003109964230000062
(3) the method only needs a few steps to complete the isolation of the abnormal value. But the number of steps required to isolate the observed value x is affected by the number of samples n. To eliminate this effect, normalized outliers s (x, n) are defined:
Figure BDA0003109964230000063
wherein (c) (n) is represented by:
Figure BDA0003109964230000064
h (i) is the harmonic number, about equal to:
H(i)≈ln(i)+0.5772156649 (5)
it can be shown that c (n) is the average number of steps required to separate one sample from the other n samples, which provides a normalization factor such that the value of s is independent of the number of samples n.
(4) In the training process, a given training set is divided recursively, and the training is stopped when abnormal data in a sample is isolated or reaches the height of a specified tree to generate a local model. The tree height h is approximately equal to the average tree height and can be defined as:
h＝ceiling(log2ψ) (6)
where ψ represents the subsample size and CEILING represents the CEILING function. Data points with a path length shorter than the average path length have a greater probability of falling in the abnormal region, thus allowing the tree to grow to the average tree height effectively isolating the abnormal data points.
The DBSCAN is used as an algorithm for processing abnormal data of the fan, the density is used as a dividing basis, the number of clusters is not required to be determined in advance, but two important parameters in the algorithm, namely a clustering radius epsilon and a density threshold Minpts in a radius area, need to be set in advance, and if the set parameter values are not suitable for a data set, the clustering effect is not obvious. The setting of the two parameters is particularly important and is kept unchanged all the time in the operation process. The basic idea is as follows: and calculating the number of the neighborhood objects by taking epsilon as a radius, classifying the neighborhood objects into a class if the number reaches a density threshold, and then connecting the high-density areas into clusters. Let X be { p ═ p1,p2,L pnIs then pi、pjDistance formula dist (p) between two pointsi,pj) The algorithm is defined as follows:
(1) epsilon neighborhood: neighborhood Nε(pi) Is expressed as Nε(pi)＝{pj∈X|dist(pi,pj) ≦ ε, is piAs the center of the circle, epsilon is the area of the radius.
(2) Core object: p is a radical ofiNeighborhood Nε(pi) If the number of the midpoints is greater than or equal to MinPts, then p is callediIs a core object;
(3) the direct density can reach: if p isj∈Nε(pi) And p isiIs a core point, then called pjIs from piDirect density is achievable as shown in figure 3 a.
(4) The density can reach: if the sequence { pi,pi+1,K,pjIn ∈ X, pi+1From piWhen the direct density is reached, it is called pjIs from piThe density can be achieved as shown in figure 3 b.
(5) Density connection: point of presence pkE.g. X, if pi，pjAll can be selected from pkWhen the density is up, it is called piAnd pjAre density connected as shown in figure 3 c.
S2.1.1: dividing data X screened by fan state codes into t groups, selecting current group data, randomly extracting psi samples, randomly selecting one sample as a node, randomly selecting one value in the characteristic value field, adopting a binary division method for the psi samples, and dividing the psi samples into a left branch if the extracted sample value is smaller than the value, otherwise, dividing the psi samples into a right branch.
S2.1.2: judging whether the current group data is inseparable or whether the tree height is larger than a formula 6, if the current group data is inseparable or not, returning to the step (1); if the condition is satisfied, the data score is calculated by formula 3, and when the score is close to 1, it is judged to be abnormal. When the score approaches 0.5, it cannot be determined whether the data is abnormal, and when the score approaches 0, it is determined as normal data.
S2.1.3: removing part of abnormal data through the step (2), inputting the rest data into a DBSCAN model, initializing parameters epsilon and MinPts, and selecting one data p from the obtained data setiAnd is marked as read, the neighborhood of the marked data is checkedAnd (4) the number.
S2.1.4: if | NEps(pi) If the value is greater than or equal to MinPts, p is a core object, and then all data points connected with the density can be searched according to the density and marked to be read.
S2.1.5: if not satisfy | NEps(pi) If the density is equal to or more than MinPts, p is not a core object, the point p is marked as read, class label processing is not carried out, later data reading is not considered, and when other data is processed and the density can be reached and is connected, the processing is carried out.
S2.1.6: and (5) repeating the steps (3) to (5), and treating the data sample without the class mark as abnormal data until all subsets are iterated.
Fig. 4 shows the abnormal data recognition result using the isolated forest and DBSCAN.
S2.2: data normalization
0-1 normalization, by quantizing the raw data to map it between [0,1], is calculated as follows:
Figure BDA0003109964230000081
x′iis a normalized value, xiAs raw data, xmaxAnd xminThe maximum and minimum values before normalization.
S3: establishing a regression model;
in order to facilitate analysis of the yaw static errors and the fan performances of four fans of a yaw system, taking a class a fan as an example, by referring to technical documents of the class a fan, the existing control strategy is that the yaw threshold time exceeds 160 seconds, and when a beta angle (an included angle between a cabin and an average wind direction in the period of time) exceeds 8 degrees, the cabin performs yaw, so that alpha (-8,8) is divided into 16 sections in a segmented manner, and fitting is performed on the obtained wind speed-power dispersion point of each section.
And performing polynomial fitting on each obtained wind speed-power scattered point to obtain 16 wind speed-power curves, and analyzing which curve has the maximum power under a certain wind speed condition, wherein the corresponding curve is the yaw error value.
Fitting the wind speed-power curve by adopting cubic spline to construct a cubic function Sk(x) In [ a, b)]The continuous second derivative is provided, and the second derivative value parameter S' on the node is selected3(xi)＝Mi(i is 0,1L, n), then the function S3(xi)＝yi(i ═ 0,1, L, n) in segment [ x-i-1,xi]The above needs are satisfied:
S3(xi-1)＝yi-1,S3(xi)＝yi
S″3(xi-1)＝Mi-1,S″3(xi)＝Mi (8)
interpolation using lagrange is:
Figure BDA0003109964230000091
in the formula, hi＝xi-xi-1。
Two integrations were performed for equation 9, and after differentiating:
Figure BDA0003109964230000092
will S3'(xi-0)＝S3'(xi+0) into equation 10:
Figure BDA0003109964230000093
the above formula can be represented as:
(1-ai)Mi-1+2Mi+aiMi+1＝gi(i＝1,2,L n-1) (12)
the free boundary condition is the left boundary [ x ] at the origin0,x1]Upper, x is x0The time-lead formula 12 is as follows:
Figure BDA0003109964230000101
if S3' (0) known as x, which is given by the formula 3.160The following can be obtained:
2M0+0×M1＝2×S″3(x0) (14)
the boundary conditions of the starting point are:
2M0+a0M1＝g(0) (15)
wherein, given y ″)0When a is0＝0,g0＝2y″0(ii) a Given y'0When the temperature of the water is higher than the set temperature,
Figure BDA0003109964230000102
similarly, the boundary conditions of the end point are:
anMn-1+2Mn＝gn (16)
wherein, given y ″)nWhen a isn＝0,gn＝2y″n(ii) a Given y'nWhen the temperature of the water is higher than the set temperature,
Figure BDA0003109964230000103
constitutes a solution problem:
Figure BDA0003109964230000104
solving the equation to obtain M0,M1,L MnThe obtained power curve model is shown in fig. 6, wherein the obtained cubic spline fitting function formula is:
f(x)＝0.3105x3+0.4633x2+0.1538x+0.009898 (18)
the wind power curve fitted by cubic spline is shown in fig. 5.
S4: and (5) obtaining the static deviation of the yaw system.
Based on the data of the fans with good conditions of the fan type A, the fan type B, the fan type C and the fan type D in 2019, deviation values of the fans with the four types are obtained. Taking class-A fans as an example, fitting the wind power dispersion points in 16 intervals to obtain 16 wind speed-power curves, as shown in FIG. 6, the uppermost lines are [ -5, -4) and [ -4, -3), so that the values are taken to be-4 °. In the same way, the yaw error of the other three types of fans is-7 degrees, the yaw error of the C type of fan is-6 degrees, the yaw error of the D type of fan is-6 degrees, and the yaw performance pair of the four types of fans is shown in FIG. 7.
In summary, according to the technical scheme of the embodiment of the invention, for discrete abnormal data in a data set, the isolated forest algorithm can be used for well removing the abnormal points, and for accumulated abnormal data points, the DBSCAN clustering algorithm can be used for well removing the abnormal points. The invention designs a combined recognition model of the isolated forest and the DBSCAN to process abnormal data, and can simultaneously remove discrete abnormal data and accumulation abnormal data in a data set. In addition, the model provided by the embodiment of the invention is suitable for measuring the yaw errors of different types of units, and can realize comparison of the yaw performances of different types of fans.
Apparatus embodiment one
According to an embodiment of the present invention, there is provided a yaw error measurement apparatus for a multi-type wind turbine, fig. 8 is a schematic diagram of the yaw error measurement apparatus for the multi-type wind turbine according to the embodiment of the present invention, and as shown in fig. 8, the yaw error measurement apparatus for the multi-type wind turbine according to the embodiment of the present invention specifically includes:
the acquisition module 80 is configured to acquire data of multiple types of fans and perform preprocessing on the data of the multiple types of fans; the obtaining module 80 is specifically configured to: cleaning abnormal data by adopting an isolated forest and DBSCAN clustering algorithm, and carrying out normalization treatment:
and the processing module 82 is used for carrying out interval processing on the preprocessed multi-type fan data, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of each type of fan, and acquiring the yaw error of each type of fan according to the optimal wind speed-power curve.
The above apparatus may further comprise:
and the comparison module is used for comparing the optimal wind speed-power curves of the various types of fans to obtain the fan type with the optimal yaw performance after the processing module acquires the yaw errors of the various types of fans according to the optimal wind speed-power curves.
The embodiment of the present invention is an apparatus embodiment corresponding to the above method embodiment, and specific operations of each module may be understood with reference to the description of the method embodiment, which is not described herein again.
Device embodiment II
An embodiment of the present invention provides a yaw error measurement apparatus for a multi-type fan, as shown in fig. 9, including: a memory 90, a processor 92 and a computer program stored on the memory 90 and executable on the processor 92, which computer program when executed by the processor 92 performs the steps as described in the method embodiments.
Device embodiment III
An embodiment of the present invention provides a computer-readable storage medium, on which an implementation program for information transmission is stored, and the program, when executed by the processor 92, implements the steps as described in the method embodiment.
The computer-readable storage medium of this embodiment includes, but is not limited to: ROM, RAM, magnetic or optical disks, and the like.
It should be noted that the embodiment related to the storage medium in this specification and the embodiment related to the service providing method based on the block chain in this specification are based on the same inventive concept, and therefore, for specific implementation of this embodiment, reference may be made to implementation of the yaw error measurement method of the corresponding multi-type wind turbine, and repeated details are not repeated.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of this document and is not intended to limit this document. Various modifications and changes may occur to those skilled in the art from this document. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.

Claims (10)

1. The utility model provides a method for measuring yaw error of polymorphic type fan which characterized in that includes:
acquiring multi-type fan data, and preprocessing the multi-type fan data;
and carrying out interval processing on the preprocessed data of the various types of fans, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of the various types of fans, and acquiring the yaw error of the various types of fans according to the optimal wind speed-power curve.
2. The method of claim 1, wherein after obtaining yaw errors of various types of wind turbines from the optimal wind speed-power curve, the method further comprises:
and comparing the optimal wind speed-power curves of various types of fans to obtain the fan type with the optimal yaw performance.
3. The method of claim 1, wherein preprocessing the multi-type wind turbine data specifically comprises:
and cleaning abnormal data by adopting an isolated forest and DBSCAN clustering algorithm, and performing normalization processing.
4. The method as claimed in claim 1, wherein the cleaning of the abnormal data by using the isolated forest and DBSCAN clustering algorithm and the normalization process specifically comprise:
step 1, an isolated forest consisting of t isolated trees is represented according to formula 1:
IF∈{t1,...,tTformula 1;
wherein T is the total number of the isolated trees.
For each tree t, the number of iterations h required to isolate an observation x is calculatedt(x) Then the average number of steps required to isolate sample x in an isolated forest is expressed according to equation 2:
Figure FDA0003109964220000011
the normalized outlier s (x, n) is defined according to equation 3 and equation 4:
Figure FDA0003109964220000021
Figure FDA0003109964220000022
where n is the number of samples, x is the isolated observed value, H (i) is the harmonic number, H (i) is ≈ ln (i) +0.5772156649, c (n) is the number of averaging steps required to separate one sample from the other n samples, and provides a normalization factor such that the value of s is independent of the number of samples n
In the training process, a given training set is recursively divided, when abnormal data in a sample is isolated or reaches the height of a designated tree to generate a local model, the training is stopped, and the height h of the tree is determined to be approximately equal to the average height according to a formula 5:
h＝ceiling(log2ψ) equation 5;
wherein ψ represents a sub-sample size and CEILING represents a CEILING function;
let DBSCAN algorithm data set X ═ { p ═ p1,p2,L pnIs then pi、pjDistance formula dist (p) between two pointsi,pj) The DBSCAN algorithm is defined as follows: neighborhood Nε(pi) Is expressed as Nε(pi)＝{pj∈X|dist(pi,pj) ≦ ε, is piAs the center of a circle, epsilon as the area of radius, piNeighborhood Nε(pi) If the number of the midpoints is greater than or equal to MinPts, then p is callediIs a core object, if pj∈Nε(pi) And p isiIs a core point, then called pjIs from piDirect density is achievable if the sequence { p }i,pi+1,K,pjIn ∈ X, pi+1From piWhen the direct density is reached, it is called pjIs from piDensity of achievable, point of presence pkE.g. X, if pi，pjAll can be selected from pkWhen the density is up, it is called piAnd pjAre density linked;
step 2, dividing the data X screened by the fan state codes into t groups, selecting current group data, randomly extracting psi samples, randomly selecting one sample as a node, randomly selecting a value in the characteristic value range, adopting a binary division method for the psi samples, and dividing the psi samples into a left branch if the sample value is smaller than the value, otherwise, dividing the psi samples into a right branch;
step 3, judging whether the current group data is inseparable or whether the height of the tree is larger than a formula 5, and returning to the step 2 if the current group data is inseparable or the height of the tree is not larger than the formula 5; if the condition is met, calculating the score of the data through a formula 3, judging the data to be abnormal when the score is close to 1, judging whether the data is abnormal when the score is close to 0.5, and judging the data to be normal data when the score is close to 0;
step 4, removing part of abnormal data through the step 3, inputting the rest data into the DBSCAN model, initializing parameters epsilon and MinPts, and selecting one data p from the obtained data setiAnd recording as read, and checking the neighborhood number of the marked data;
step 5, if | NEps(pi) If the value is more than or equal to MinPts, p is a core object, and then all data points connected with the density can be searched according to the density and marked to be read;
step 6, if the absolute value of N is not satisfiedEps(pi) If the density of other data can be reached and the density is connected, processing is carried out;
step 7, repeating the steps 4-6, and treating the data sample without the class mark as abnormal data until all subsets are iterated;
step 8, according to formula 6, performing 0-1 normalization, and mapping the original data between [0,1] by quantizing, the calculation method is as follows:
Figure FDA0003109964220000031
wherein, x'iIs a normalized value, xiAs raw data, xmaxAnd xminThe maximum and minimum values before normalization.
5. The method according to claim 1, wherein the pre-processed data of the multiple types of fans are subjected to interval processing, a cubic spline method is adopted to perform polynomial fitting on the wind speed-power scattering point of each interval, an optimal wind speed-power curve of each type of fan is selected, and obtaining the yaw error of each type of fan according to the optimal wind speed-power curve specifically comprises:
carrying out interval processing on the preprocessed multi-type fan data, fitting a wind speed-power curve by adopting a cubic spline, and constructing a cubic function Sk(x) In [ a, b)]The continuous second derivative is provided, and the second derivative value parameter S' on the node is selected3(xi)＝Mi(i is 0,1L, n), then the function S3(xi)＝yi(i ═ 0,1, L, n) in segment [ x-i-1,xi]The above needs to satisfy equation 7:
S3(xi-1)＝yi-1,S3(xi)＝yi
S″3(xi-1)＝Mi-1,S″3(xi)＝Miequation 7;
interpolation is performed using lagrange according to equation 8:
Figure FDA0003109964220000041
wherein h isi＝xi-xi-1。
According to equation 9, equation 8 is integrated twice and then differentiated:
Figure FDA0003109964220000042
is prepared from S'3(xi-0)＝S′3(xi+0) into equation 9 yields equation 10:
Figure FDA0003109964220000043
equation 10 is expressed as equation 12:
(1-ai)Mi-1+2Mi+aiMi+1＝gi(i＝1,2,L n-1) equation 11;
assume a free boundary condition is the left boundary [ x ] at the start point0,x1]Upper, x is x0Time-import equation 11 yields equation 12:
Figure FDA0003109964220000044
if S'3(0) It is known to take x ═ x0To obtain equation 13:
2M0+0×M1＝2×S″3(x0) Equation 13;
the boundary condition for determining the starting point according to equation 13 is equation 14:
2M0+a0M1g (0) formula 14;
wherein, given y ″)0When a is0＝0,g0＝2y″0(ii) a Given y'0When the temperature of the water is higher than the set temperature,
Figure FDA0003109964220000051
similarly, the boundary condition of the endpoint is determined according to equation 15:
anMn-1+2Mn＝gnequation 15;
wherein, given y ″)nWhen a isn＝0,gn＝2y″n(ii) a Given y'nWhen the temperature of the water is higher than the set temperature,
Figure FDA0003109964220000052
the solution problem is constructed according to equation 16:
Figure FDA0003109964220000053
solving equation formula 16 to obtain M0,M1,L MnAnd obtaining a power curve model, wherein the obtained cubic spline fitting function formula is formula 17:
f(x)＝0.3105x3+0.4633x2+0.1538x +0.009898 formula 17.
6. The utility model provides a yaw error measuring device of polymorphic type fan which characterized in that includes:
the acquisition module is used for acquiring the data of the multiple types of fans and preprocessing the data of the multiple types of fans;
and the processing module is used for carrying out interval processing on the preprocessed multi-type fan data, carrying out polynomial fitting on the wind speed-power scattering points of each interval by adopting a cubic spline method, selecting an optimal wind speed-power curve of each type of fan, and acquiring the yaw error of each type of fan according to the optimal wind speed-power curve.
7. The apparatus of claim 6, further comprising:
and the comparison module is used for comparing the optimal wind speed-power curves of the various types of fans to obtain the fan type with the optimal yaw performance after the processing module acquires the yaw errors of the various types of fans according to the optimal wind speed-power curves.
8. The apparatus of claim 6,
the acquisition module is specifically configured to: cleaning abnormal data by adopting an isolated forest and DBSCAN clustering algorithm, and carrying out normalization treatment:
step 1, an isolated forest consisting of t isolated trees is represented according to formula 1:
IF∈{t1,...,tTformula 1;
wherein T is the total number of the isolated trees.
For each tree t, the number of iterations h required to isolate an observation x is calculatedt(x) Then the average number of steps required to isolate sample x in an isolated forest is expressed according to equation 2:
Figure FDA0003109964220000061
the normalized outlier s (x, n) is defined according to equation 3 and equation 4:
Figure FDA0003109964220000062
Figure FDA0003109964220000063
where n is the number of samples, x is the isolated observed value, H (i) is the harmonic number, H (i) is ≈ ln (i) +0.5772156649, c (n) is the number of averaging steps required to separate one sample from the other n samples, and provides a normalization factor such that the value of s is independent of the number of samples n
In the training process, a given training set is recursively divided, when abnormal data in a sample is isolated or reaches the height of a designated tree to generate a local model, the training is stopped, and the height h of the tree is determined to be approximately equal to the average height according to a formula 5:
h＝ceiling(log2ψ) equation 5;
wherein ψ represents a sub-sample size and CEILING represents a CEILING function;
let DBSCAN algorithm data set X ═ { p ═ p1,p2,L pnIs then pi、pjDistance formula dist (p) between two pointsi,pj) The DBSCAN algorithm is defined as follows: neighborhood Nε(pi) Is expressed as Nε(pi)＝{pj∈X|dist(pi,pj) ≦ ε, is piAs the center of a circle, epsilon as the area of radius, piNeighborhood Nε(pi) If the number of the midpoints is greater than or equal to MinPts, then p is callediIs a core object, if pj∈Nε(pi) And p isiIs a core point, then called pjIs from piDirect density is achievable if the sequence { p }i,pi+1,K,pjIn ∈ X, pi+1From piWhen the direct density is reached, it is called pjIs from piDensity of achievable, point of presence pkE.g. X, if pi，pjAll can be selected from pkWhen the density is up, it is called piAnd pjAre density linked;
step 2, dividing the data X screened by the fan state codes into t groups, selecting current group data, randomly extracting psi samples, randomly selecting one sample as a node, randomly selecting a value in the characteristic value range, adopting a binary division method for the psi samples, and dividing the psi samples into a left branch if the sample value is smaller than the value, otherwise, dividing the psi samples into a right branch;
step 3, judging whether the current group data is inseparable or whether the height of the tree is larger than a formula 5, and returning to the step 2 if the current group data is inseparable or the height of the tree is not larger than the formula 5; if the condition is met, calculating the score of the data through a formula 3, judging the data to be abnormal when the score is close to 1, judging whether the data is abnormal when the score is close to 0.5, and judging the data to be normal data when the score is close to 0;
step 4, removing part of abnormal data through the step 3, inputting the rest data into the DBSCAN model, initializing parameters epsilon and MinPts, and selecting one data p from the obtained data setiAnd recording as read, and checking the neighborhood number of the marked data;
step 5, if | NEps(pi) If the value is more than or equal to MinPts, p is a core object, and then all data points connected with the density can be searched according to the density and marked to be read;
step 6, if the absolute value of N is not satisfiedEps(pi) If the density of other data can be reached and the density is connected, processing is carried out;
step 7, repeating the steps 4-6, and treating the data sample without the class mark as abnormal data until all subsets are iterated;
step 8, according to formula 6, performing 0-1 normalization, and mapping the original data between [0,1] by quantizing, the calculation method is as follows:
Figure FDA0003109964220000081
wherein, x'iIs a normalized value, xiAs raw data, xmaxAnd xminThe maximum value and the minimum value before normalization;
the processing module is specifically configured to:
carrying out interval processing on the preprocessed multi-type fan data, fitting a wind speed-power curve by adopting a cubic spline, and constructing a cubic function Sk(x) In [ a, b)]The continuous second derivative is provided, and the second derivative value parameter S' on the node is selected3(xi)＝Mi(i is 0,1L, n), then the function S3(xi)＝yi(i ═ 0,1, L, n) in segment [ x-i-1,xi]The above needs to satisfy equation 7:
S3(xi-1)＝yi-1,S3(xi)＝yi
S″3(xi-1)＝Mi-1,S″3(xi)＝Miequation 7;
interpolation is performed using lagrange according to equation 8:
Figure FDA0003109964220000082
wherein h isi＝xi-xi-1。
According to equation 9, equation 8 is integrated twice and then differentiated:
Figure FDA0003109964220000083
is prepared from S'3(xi-0)＝S′3(xi+0) into equation 9 yields equation 10:
Figure FDA0003109964220000084
equation 10 is expressed as equation 12:
(1-ai)Mi-1+2Mi+aiMi+1＝gi(i ═ 1,2, L n-1) formula 11;
assume a free boundary condition is the left boundary [ x ] at the start point0,x1]Upper, x is x0Time-import equation 11 yields equation 12:
Figure FDA0003109964220000091
if S'3(0) It is known to take x ═ x0To obtain equation 13:
2M0+0×M1＝2×S″3(x0) Equation 13;
the boundary condition for determining the starting point according to equation 13 is equation 14:
2M0+a0M1g (0) formula 14;
wherein, given y ″)0When a is0＝0,g0＝2y″0(ii) a Given y'0When the temperature of the water is higher than the set temperature,
Figure FDA0003109964220000092
similarly, the boundary condition of the endpoint is determined according to equation 15:
anMn-1+2Mn＝gnequation 15;
wherein, giveDetermine ynWhen a isn＝0,gn＝2y″n(ii) a Given y'nWhen the temperature of the water is higher than the set temperature,
Figure FDA0003109964220000093
the solution problem is constructed according to equation 16:
Figure FDA0003109964220000094
solving equation formula 16 to obtain M0,M1,L MnAnd obtaining a power curve model, wherein the obtained cubic spline fitting function formula is formula 17:
f(x)＝0.3105x3+0.4633x2+0.1538x +0.009898 formula 17.
9. The utility model provides a yaw error measuring device of polymorphic type fan which characterized in that includes: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method of yaw error measurement of a multi-type wind turbine as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium, wherein the computer-readable storage medium has stored thereon an information transfer implementing program, which when executed by a processor implements the steps of the yaw error measurement method of a multi-type wind turbine according to any one of claims 1 to 5.
CN202110647957.5A 2021-06-10 2021-06-10 Yaw error measurement method and device for multi-type fans Active CN113323818B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110647957.5A CN113323818B (en) 2021-06-10 2021-06-10 Yaw error measurement method and device for multi-type fans

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110647957.5A CN113323818B (en) 2021-06-10 2021-06-10 Yaw error measurement method and device for multi-type fans

Publications (2)

Publication Number Publication Date
CN113323818A true CN113323818A (en) 2021-08-31
CN113323818B CN113323818B (en) 2024-01-19

Family

ID=77420465

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110647957.5A Active CN113323818B (en) 2021-06-10 2021-06-10 Yaw error measurement method and device for multi-type fans

Country Status (1)

Country Link
CN (1) CN113323818B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114926082A (en) * 2022-06-07 2022-08-19 平安科技（深圳）有限公司 Artificial intelligence-based data fluctuation early warning method and related equipment

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013152776A1 (en) * 2012-04-13 2013-10-17 Kk-Electronic A/S A configuration system for a wind turbine control system
CN103440405A (en) * 2013-08-08 2013-12-11 广东电网公司电力科学研究院 Method and system for steady-state modeling of wind power plant based on measured data
CN109139363A (en) * 2017-06-15 2019-01-04 南京工程学院 A kind of maximum power point-tracing control method promoting multi-model wind mill performance
CN109488528A (en) * 2018-11-23 2019-03-19 华润电力技术研究院有限公司 A kind of method of adjustment and device of fan yaw system
CN109667727A (en) * 2018-11-18 2019-04-23 浙江大学 A kind of identification of Wind turbines yaw error inherent variability and compensation method based on power curve analysis
CN110046665A (en) * 2019-04-17 2019-07-23 成都信息工程大学 Based on isolated two abnormal classification point detecting method of forest, information data processing terminal
KR20190087095A (en) * 2018-01-16 2019-07-24 군산대학교산학협력단 Method and system for yaw control of WindTurbin
CN110067708A (en) * 2019-05-13 2019-07-30 北京天泽智云科技有限公司 A method of it is not positive to wind using power curve identification yaw
EP3569859A1 (en) * 2018-05-14 2019-11-20 Laborelec CVBA Wind turbine efficiency improvement methods related to wind sensor misalignment
CN111563543A (en) * 2020-04-26 2020-08-21 国网冀北电力有限公司电力科学研究院 Method and device for cleaning wind speed-generated power data of wind turbine generator
CN112818604A (en) * 2021-02-05 2021-05-18 河海大学 Wind turbine generator risk degree assessment method based on wind power prediction
CN112905583A (en) * 2021-04-01 2021-06-04 辽宁工程技术大学 High-dimensional big data outlier detection method

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013152776A1 (en) * 2012-04-13 2013-10-17 Kk-Electronic A/S A configuration system for a wind turbine control system
CN103440405A (en) * 2013-08-08 2013-12-11 广东电网公司电力科学研究院 Method and system for steady-state modeling of wind power plant based on measured data
CN109139363A (en) * 2017-06-15 2019-01-04 南京工程学院 A kind of maximum power point-tracing control method promoting multi-model wind mill performance
KR20190087095A (en) * 2018-01-16 2019-07-24 군산대학교산학협력단 Method and system for yaw control of WindTurbin
EP3569859A1 (en) * 2018-05-14 2019-11-20 Laborelec CVBA Wind turbine efficiency improvement methods related to wind sensor misalignment
CN109667727A (en) * 2018-11-18 2019-04-23 浙江大学 A kind of identification of Wind turbines yaw error inherent variability and compensation method based on power curve analysis
CN109488528A (en) * 2018-11-23 2019-03-19 华润电力技术研究院有限公司 A kind of method of adjustment and device of fan yaw system
CN110046665A (en) * 2019-04-17 2019-07-23 成都信息工程大学 Based on isolated two abnormal classification point detecting method of forest, information data processing terminal
CN110067708A (en) * 2019-05-13 2019-07-30 北京天泽智云科技有限公司 A method of it is not positive to wind using power curve identification yaw
CN111563543A (en) * 2020-04-26 2020-08-21 国网冀北电力有限公司电力科学研究院 Method and device for cleaning wind speed-generated power data of wind turbine generator
CN112818604A (en) * 2021-02-05 2021-05-18 河海大学 Wind turbine generator risk degree assessment method based on wind power prediction
CN112905583A (en) * 2021-04-01 2021-06-04 辽宁工程技术大学 High-dimensional big data outlier detection method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵嫚 等: "基于模糊聚类和孤立森林的用电数据异常检测", 《陕西理工大学学报（自然科学版）》, vol. 36, no. 4, pages 38 - 43 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114926082A (en) * 2022-06-07 2022-08-19 平安科技（深圳）有限公司 Artificial intelligence-based data fluctuation early warning method and related equipment

Also Published As

Publication number Publication date
CN113323818B (en) 2024-01-19

Similar Documents

Publication Publication Date Title
CN111275288B (en) XGBoost-based multidimensional data anomaly detection method and device
CN108590982B (en) Abnormal data processing method for limited power operation of wind turbine generator
CN111444615B (en) Photovoltaic array fault diagnosis method based on K nearest neighbor and IV curve
CN116861354A (en) Abnormality identification and mode distinguishing method and system for monitoring data of power transformer
CN110795690A (en) Wind power plant operation abnormal data detection method
Yesilbudak Partitional clustering-based outlier detection for power curve optimization of wind turbines
CN116522268B (en) Line loss anomaly identification method for power distribution network
CN113822418A (en) Wind power plant power prediction method, system, device and storage medium
CN111144440A (en) Method and device for analyzing daily power load characteristics of special transformer user
CN116610938B (en) Method and equipment for detecting unsupervised abnormality of semiconductor manufacture in curve mode segmentation
CN113323818A (en) Yaw error measuring method and device for multiple types of fans
CN116448161A (en) Artificial intelligence-based environment monitoring equipment fault diagnosis method
CN117113264B (en) Method for detecting abnormality of dissolved oxygen meter of sewage plant on line in real time
CN108459585B (en) Power station fan fault diagnosis method based on sparse local embedded deep convolutional network
CN116910556A (en) Power plant equipment abnormality detection method, training device, equipment and medium
CN114167730B (en) Method, computer and storage medium for evaluating overall health state of blower of thermal power generating unit
CN115730255A (en) Motor fault diagnosis and analysis method based on transfer learning and multi-source information fusion
CN113642465A (en) Bearing health assessment method based on relational network
CN110175639B (en) Short-term wind power prediction method based on feature selection
CN114033736A (en) Fan fault monitoring system based on air pressure pulse signals
CN114077924A (en) Wind power prediction gale data enhancement method considering extreme gale weather
CN110807555A (en) Method for predicting rotor falling in rotating unit based on visual guidance algorithm
CN110826795B (en) Day-ahead load prediction method for extreme temperature weather day bus
CN111860567B (en) Construction method of blade image recognition model
CN111507495A (en) Method and device for predicting missing wind measurement data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant